Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds value by disclosing what each result conveys (per-model capabilities) and an anti-hallucination constraint. It does not discuss pagination defaults or how limits truncate results, which the schema covers only partially.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with zero filler; the capability list is front-loaded and the actionable instruction follows. The opening noun phrase lacks a verb, a minor structural weakness, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-required-parameter, read-only list tool with full schema coverage and no output schema, the description supplies enough: what is listed, what fields matter, and how the ids are consumed. Only result-volume/pagination behavior is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so use/limit/query are already documented with an enum and bounds. The description adds no extra semantics about filtering or result ordering beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource precisely (AI models usable by a prompt step or an agent) and enumerates the capability attributes returned (images, vision, reasoning, tool calling, JSON output). It is a fragment rather than a verb-led sentence, but an agent can still distinguish it from siblings like list_agent_tools or list_step_types.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete downstream usage: take a model's id and use it when adding/editing a prompt step or changing an agent's model, plus an explicit prohibition ("never guess one"). There is no stated when-not-to-use case or named alternative, which keeps it just below the top score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.